bmad-plus 0.13.0 → 0.16.0

package/README.md

@@ -1,561 +1,184 @@
-# 🚀 BMAD+ — Augmented Multi-Agent AI Framework
+# BMAD+
 
-[![Version](https://img.shields.io/badge/version-0.13.0-blue.svg)](CHANGELOG.md)
-[![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
-[![License](https://img.shields.io/badge/license-MIT-yellow.svg)](LICENSE)
+[![Version](https://img.shields.io/badge/version-0.16.0-blue)](https://www.npmjs.com/package/bmad-plus)
 
-<div align="center">
-  🌐 <b>English</b> | <a href="readme-international/README.fr.md">Français</a> | <a href="readme-international/README.es.md">Español</a> | <a href="readme-international/README.de.md">Deutsch</a>
-</div>
+**Version 0.16.0** · Node.js `>=20.0.0` · MIT
 
-> **Multi-role agents · 9 modular packs · Autopilot mode · Parallel execution**
-> Smart fork of [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) — Self-activating agents with 3-level context detection, GRC compliance (Shield), full SDLC pipeline (Dev Studio), OSINT intelligence, SEO audit, persistent cross-session memory, and a 10-language CLI installer.
+Project-local AI development workflows with clear roles, shared context, safe updates and coding-tool adapters
 
----
-
-## 📋 Table of Contents
-
-Repository validation: **709 JavaScript tests** (`npm test`). Uninstall preserves project memory and customized files; use `--yes` for installation or removal without a terminal.
+[Website](https://bmad-plus.rochetta.fr/) · [Get started](https://bmad-plus.rochetta.fr/docs/#start) · [Examples](https://bmad-plus.rochetta.fr/docs/#examples) · [What’s new](https://bmad-plus.rochetta.fr/docs/#news)
 
-- [Why BMAD+?](#-why-bmad-)
-- [Quick Start](#-quick-start)
-- [Architecture](#-architecture)
-- [The 47 Agents](#the-47-agents)
-- [Pack System](#-pack-system)
-- [Innovations](#-innovations)
-- [Supported IDEs](#-supported-ides)
-- [Project Structure](#-project-structure)
-- [Configuration](#-configuration)
-- [Version History](#-version-history)
-- [License](#-license)
+BMAD+ installs project instructions, roles and workflows for your existing AI coding tool. Default execution is host-managed: your tool supplies the model, permissions, command execution and any parallel-agent capability. Nexus can also launch an explicitly planned local command or Codex CLI process under a foreground supervisor, record its result and require independent checks before acceptance. Host permissions still apply; there is no background scheduler or universal host lifecycle integration. Model subscriptions and API access are separate.
 
----
-
-## 💡 Why BMAD+?
+Adapters: Claude Code, Gemini CLI, Antigravity, Cursor, Codex CLI, OpenCode, Aider.
 
-BMAD-METHOD is an excellent framework with 9 specialized agents. But for a solo developer or a small team, 9 agents is too fragmented. BMAD+ solves this problem:
+## Get started
 
-| BMAD-METHOD | BMAD+ |
-|---|---|
-| 9 specialized agents | **47 agents** across 9 packs |
-| Manual activation only | **Intelligent auto-activation** at 3 levels |
-| No automated pipeline | **Autopilot Mode**: idea → delivery |
-| Sequential execution | **Supervised parallelism** |
-| No persistent memory | **Cross-session brain** with project scanner |
-| 1-2 IDEs supported | **7 IDEs** with auto-detection |
-| 1 module | **9 modular packs** (Core, OSINT, Shield, Dev Studio, SEO, Memory...) |
+Requires Node.js `>=20.0.0`. Optional packs may need additional runtimes or API access. Run terminal commands from your project folder.
 
----
+### 1. Open your project folder
 
-## ⚡ Quick Start
+Use a terminal in the repository you want to work on, then check your Node.js version. Keep your usual version control workflow.
 
-### Installation in an existing project
+**In your project terminal:**
 
-```bash
-npx bmad-plus install
+```sh
+node --version
 ```
 
-The installer:
-1. Automatically detects installed IDEs (Claude Code, Gemini CLI, Codex, etc.)
-2. Offers packs to install (Core, OSINT, Maker, Audit)
-3. Generates adapted configuration files
-4. Creates artifact folders
+The command should report v20 or newer. Install or update Node.js separately if needed.
 
-### Usage after installation
+### 2. Install BMAD+ and choose your tools
 
-#### 💬 Who to talk to?
+Run the installer. Select the adapters for the AI tools you use and the packs your project needs. Core contains Atlas, Forge, Sentinel and Nexus.
 
-**📊 Strategy & Discovery**
+**In your project terminal:**
 
-| You want to... | Talk to | Example |
-|---|---|---|
-| Brainstorm a project idea | **Atlas** 🎯 | `Atlas, I have a project idea: a billing SaaS` |
-| Market/domain research | **Atlas** 🎯 | `Atlas, analyze the market for AI note-taking apps` |
-| Create a PRD / Product Brief | **Atlas** 🎯 | `Atlas, create the PRD for my project` |
-| Design UX wireframes | **Atlas** 🎯 | `Atlas, design the UX for the onboarding flow` |
+```sh
+npx bmad-plus@0.16.0 install
+```
 
-**🏗️ Architecture & Development**
+The installer creates the agent instructions, shared project spine and selected tool adapters. Optional packs may need additional runtimes or API access.
 
-| You want to... | Talk to | Example |
-|---|---|---|
-| Design technical architecture | **Forge** 🏗️ | `Forge, propose an architecture for the app` |
-| Implement a user story | **Forge** 🏗️ | `Forge, implement story AUTH-001` |
-| Write/update documentation | **Forge** 🏗️ | `Forge, document the API` |
-| Quick hotfix or small change | **Forge** 🏗️ | `Forge, quick dev: add a loading spinner` |
+### 3. Start a session in that same folder
 
-**🔍 Quality & Review**
+Open or restart your AI coding assistant in this project so it can load its adapter and AGENTS.md. Ask it to show the installed agents and workflows.
 
-| You want to... | Talk to | Example |
-|---|---|---|
-| Code review | **Sentinel** 🔍 | `Sentinel, review the auth module` |
-| Write tests (unit/E2E) | **Sentinel** 🔍 | `Sentinel, write E2E tests for checkout` |
-| UX/accessibility audit | **Sentinel** 🔍 | `Sentinel, review the UX of the dashboard` |
+**In your AI assistant:**
 
-**🎼 Project Management**
+```text
+bmad-help
+```
 
-| You want to... | Talk to | Example |
-|---|---|---|
-| Plan a sprint | **Nexus** 🎼 | `Nexus, create epics and stories for the MVP` |
-| Automate everything (A to Z) | **Nexus** 🎼 | `autopilot` then describe your project |
-| Run tasks in parallel | **Nexus** 🎼 | `parallel` — auto-detects independent tasks |
-| Sprint retrospective | **Nexus** 🎼 | `Nexus, run a retrospective on Sprint 3` |
+There is no extra BMAD+ initialization command after installation. bmad-help is a message to the assistant, not a terminal command.
 
-**🕵️ Intelligence & Specialized Packs**
+### 4. Give one role a concrete task
 
-| You want to... | Talk to | Example |
-|---|---|---|
-| Investigate a person (OSINT) | **Shadow** 🕵️ | `Shadow, investigate John Doe` |
-| Create a new BMAD+ agent | **Maker** 🧬 | `Maker, create a customer support agent` |
-| Recall past decisions/context | **Zecher** 🧠 | `Zecher, what did we decide about the auth strategy?` |
-| Session handoff summary | **Zecher** 🧠 | `Zecher, create a handoff for the next session` |
+Describe your goal, constraints and expected result. For a new idea, start with Atlas. For an existing code change, start with Forge.
 
-#### 🚀 Typical Workflow (manual mode)
+**In your AI assistant:**
 
+```text
+Atlas, help me define a small invoicing app for freelancers. Ask about the users, identify the first useful workflow and write a brief with acceptance criteria.
 ```
-1. "Atlas, brainstorm on my [project] idea"
-   → Atlas analyzes, asks questions, proposes angles
-
-2. "Atlas, create the product brief"
-   → Deliverable: _bmad-output/discovery/product-brief.md
 
-3. "Atlas, write the PRD"
-   → Deliverable: _bmad-output/discovery/prd.md
+Review the brief before asking Forge to implement one story. A clear deliverable makes progress easier to verify.
 
-4. "Forge, propose the architecture"
-   → Deliverable: _bmad-output/discovery/architecture.md
+### 5. Review the result and preserve context
 
-5. "Nexus, break down into epics and stories"
-   → Deliverable: _bmad-output/build/stories/
+Ask Sentinel to check the change against its acceptance criteria. Ask for test evidence and a short handoff so the next session can continue.
 
-6. "Forge, implement story [X]"
-   → Code generated + tests
+**In your AI assistant:**
 
-7. "Sentinel, test and review"
-   → QA report + suggestions
+```text
+Sentinel, review this change against the acceptance criteria. Check the main success and failure paths, report remaining issues and summarize what the next session needs to know.
 ```
 
-#### ⚡ Automatic Workflow (autopilot mode)
-
-```
-> autopilot
-> "A billing SaaS for SMBs with quote management"
-```
+Read the changes and test results. The assistant follows the permissions and capabilities of its host tool.
 
-Nexus automatically orchestrates everything with checkpoints for your approval.
+## Core roles
 
-#### 💬 Key Commands
+| Role | Focus | Purpose |
+| --- | --- | --- |
+| Atlas | Strategy & product | Decide what deserves to be built. |
+| Forge | Architecture & development | Make the plan concrete. |
+| Sentinel | Quality & review | Look for what the first pass missed. |
+| Nexus | Planning & coordination | Keep the work moving together. |
 
-| Command | Description |
-|----------|-------------|
-| `bmad-help` | View all available agents and skills |
-| `autopilot` | Nexus takes control of the complete pipeline |
-| `parallel` | Launch multi-agent execution in parallel |
+## Packs
 
+| Pack | What it provides |
+| --- | --- |
+| Core | Strategy, architecture, development, quality and coordination through the four core roles. |
+| OSINT | Investigation workflows for gathering public information and assessing sources. |
+| Maker | A workflow to design, validate and package your own BMAD+ agents. |
+| Shield | Specialized compliance and governance workflows, including GDPR and ISO 27001. |
+| SEO | Technical scanning, content analysis and search optimization workflows with supporting tools. |
+| Memory | Project notes, decision records and session handoffs that preserve useful context. |
+| Dev Studio | Specialized roles and workflows for product planning, design, engineering and documentation. |
+| Backup | Instructions and utilities for timestamped backups, restoration and rotation. |
+| Animated | A focused workflow for creating video-driven scrolling websites. |
 
-#### 🔧 CLI Commands
+## Examples
 
-| Command | Description |
-|---------|-------------|
-| `npx bmad-plus install` | Interactive installer with pack selection and IDE detection |
-| `npx bmad-plus scan [path]` | Discover and index projects in the global brain |
-| `npx bmad-plus memory status` | Memory health report (project + global brain) |
-| `npx bmad-plus memory export` | Export brain as portable Markdown archive |
-| `npx bmad-plus doctor` | Check installation integrity |
-| `npx bmad-plus update` | Update agents and skills (preserves config) |
-| `npx bmad-plus uninstall` | Remove BMAD+ from current project |
-| `npx bmad-plus autoconfig` | Smart project bootstrap — auto-detect, install, and configure |
+### Turn an idea into a first release
 
-#### Framework updates
+Use after you have described the users and the problem.
 
-The installed instructions ask the LLM to check once per session. Discovery uses a 24-hour cache; offline results remain unknown. Automatic updates require an explicit policy and unchanged managed files.
-
-For installations using 0.12.2 or earlier, load the new CLI once with `npx --yes bmad-plus@0.13.0 update --yes`. This explicit migration saves backups before replacing legacy files.
-
-```bash
-npx bmad-plus update-check --json
-npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.13.0"
-npx bmad-plus update --latest --auto
-npx bmad-plus update-check --offline --json
+```text
+Nexus, plan the first usable release of my appointment-booking app. Have Atlas define scope, Forge propose the smallest implementation and Sentinel define acceptance checks. List dependencies and stop at the plan review before implementation.
 ```
 
-Notification is the default. To stop checks, use `update-policy --mode off`. Customized agents and adapters are preserved; conflicts block automatic application. Older installations without file hashes require an explicit manual migration with backups. Each applied update reports a receipt; use `update --restore <receipt-id> --yes` to recover it, then reload the agent instructions.
-
-#### 🔬 Advanced Install Options
+Expected result: a prioritized plan with a small first story and explicit review points.
 
-```bash
-# Non-interactive install — all packs, auto-detect IDEs
-npx bmad-plus install --packs all --yes
+### Fix a bug in an existing project
 
-# Install without overwriting IDE configs (CLAUDE.md, GEMINI.md, etc.)
-npx bmad-plus install --tools none
+Include the failing behavior, steps to reproduce and any relevant error output.
 
-# Install specific packs only
-npx bmad-plus install --packs core,memory,osint
-
-# Install in a different directory
-npx bmad-plus install --directory /path/to/project
+```text
+Forge, investigate why saving an edited invoice creates a duplicate. Reproduce the issue, trace the cause and propose the smallest fix. Add a regression check for the real failure, then ask Sentinel to review the affected flow.
 ```
 
-> **💡 Dogfooding tip:** Use `--tools none` when installing BMAD+ into a project that already has manually maintained IDE config files. This installs agents, skills, and memory without overwriting your existing `CLAUDE.md`, `GEMINI.md`, or `AGENTS.md`.
-
-#### 🔍 Scan Options
+Expected result: a reproduced failure, a focused fix and evidence that the regression is covered.
 
-```bash
-# Scan a drive or directory for projects
-npx bmad-plus scan D:\DEV
+### Coordinate independent work
 
-# Custom thresholds for project status
-npx bmad-plus scan . --active-days 7 --paused-days 90
+Use when your host supports parallel agents and the tasks do not write to the same files.
 
-# Auto-index all without prompting
-npx bmad-plus scan D:\DEV --yes --depth 6
+```text
+Nexus, split the approved work into independent tasks. Give each role a scope, owned files and a definition of done. Use parallel agents only if this host supports them; otherwise run the tasks sequentially. Integrate the results and have Sentinel check the whole user flow.
 ```
 
-> Status legend: 🟢 **active** (modified < 30 days), 🟡 **paused** (30–180 days), ⚪ **archived** (> 180 days). Thresholds are customizable with `--active-days` and `--paused-days`.
-
----
-
-## 🏗️ Architecture
-
-```mermaid
-graph TB
-    subgraph Core["⚙️ Core Pack"]
-        AT["Atlas 🎯"]
-        FG["Forge 🏗️"]
-        SN["Sentinel 🔍"]
-        NX["Nexus 🎼"]
-    end
-
-    subgraph Packs["📦 Modular Packs"]
-        SH["Shadow 🕵️ OSINT"]
-        MK["Maker 🧬"]
-        ZC["Zecher 🧠 Memory"]
-        SD["Shield 🛡️ GRC 27 agents"]
-        DS["Dev Studio 🏗️ SDLC 6 agents"]
-        SEO["SEO Engine 🔎 3 agents"]
-        BK["Backup 🗂️"]
-        AN["Animated 🎬"]
-    end
-
-    subgraph Skills["⚡ Core Skills"]
-        AP[Autopilot]
-        PL[Parallel]
-    end
-
-    NX -->|orchestrates| AT
-    NX -->|orchestrates| FG
-    NX -->|orchestrates| SN
-    NX -->|invokes| SH
-    NX -->|invokes| MK
-    NX --> AP
-    NX --> PL
-    ZC -.->|context| NX
-```
-
----
-
-## 🎭 The 47 Agents
-
-### Atlas — Strategist 🎯
-
-**Fuses:** Analyst (Mary) + Product Manager (John)
-
-| Role | Specialty | Auto-activation |
-|------|-----------|-----------------|
-| **Analyst** | Market research, SWOT, benchmarks, domain expertise | "analyze", "market", "benchmark", new project |
-| **Product Manager** | PRD, product briefs, user stories, roadmaps | "PRD", "roadmap", "MVP", planning phase |
-
-**Capabilities:** Brainstorming (BP), Market Research (MR), Domain Research (DR), Technical Research (TR), Product Brief (CB), PRD (PR), UX Design (CU), Document Project (DP)
-
----
-
-### Forge — Architect-Dev 🏗️
-
-**Fuses:** Architect (Winston) + Developer (Amelia) + Tech Writer (Paige)
+Expected result: bounded assignments, explicit dependencies and one integrated review. Parallel execution comes from the host tool.
 
-| Role | Specialty | Auto-activation |
-|------|-----------|-----------------|
-| **Architect** | Technical design, API, scalability, stack choice | "architecture", "API", "schema", +5 files modified |
-| **Developer** | TDD implementation, code review, story execution | "implement", "code", "fix", post-architecture |
-| **Tech Writer** | Documentation, Mermaid diagrams, changelogs | "document", "README", post-implementation |
+### Have a person confirm a delivery
 
-**Capabilities:** Architecture (CA), Implementation Readiness (IR), Dev Story (DS), Code Review (CR), Quick Spec (QS), Quick Dev (QD), Document Project (DP)
-
-**Critical actions (Dev role):**
-- Read the ENTIRE story BEFORE implementation
-- Execute tasks IN ORDER
-- 100% passing tests BEFORE moving on
-- NEVER lie about tests
-
----
-
-### Sentinel — Quality 🔍
-
-**Fuses:** QA Engineer (Quinn) + UX Designer (Sally)
-
-| Role | Specialty | Auto-activation |
-|------|-----------|-----------------|
-| **QA Engineer** | API/E2E tests, edge cases, coverage, code review | "test", "QA", "bug", post-implementation |
-| **UX Reviewer** | UX evaluation, accessibility, interaction design | "UX", "interface", "responsive", frontend changes |
-
-**Capabilities:** QA Tests (QA), Code Review (CR), UX Design (CU)
-
----
-
-### Nexus — Orchestrator 🎼
-
-**Fuses:** Scrum Master (Bob) + Quick-Flow Solo Dev (Barry) + **Autopilot** (new) + **Parallel Supervisor** (new)
-
-| Role | Specialty | Auto-activation |
-|------|-----------|-----------------|
-| **Scrum Master** | Sprint planning, stories, retros, course correction | "sprint", "planning", "backlog" |
-| **Quick Flow** | Quick specs, hotfixes, minimum ceremony | "quick", "hotfix", "small fix" |
-| **Autopilot** | Pipeline automated idea→delivery with checkpoints | "autopilot", "manage everything", autopilot mode |
-| **Parallel Supervisor** | Concurrent multi-agent, conflict detection, reallocation | "parallel", independent tasks detected |
-
-**Capabilities:** Sprint Planning (SP), Create Story (CS), Epics & Stories (ES), Retrospective (ER), Course Correction (CC), Sprint Status (SS), Quick Spec (QS), Quick Dev (QD), **Autopilot (AP)**, **Parallel (PL)**
-
----
-
-### Shadow — OSINT Intelligence 🔍 *(OSINT Pack)*
-
-**Complete OSINT investigation agent.**
-
-| Capability | Description |
-|-----------|-------------|
-| **INV** | Complete investigation Phase 0→6 with scored dossier |
-| **QS** | Quick multi-engine search |
-| **LI/IG/FB** | LinkedIn, Instagram, Facebook scraping |
-| **PP** | MBTI / Big Five psychoprofile |
-| **CE** | Contact enrichment (email, phone) |
-| **DG** | Diagnostic of available tools/APIs |
-
-**Stack:** 55+ Apify actors, 7 search APIs, 100% Python stdlib, confidence grades A/B/C/D
-
----
-
-### Maker — Agent Creator 🧬 *(Maker Pack)*
-
-**Meta-agent that creates other agents.** Give it a description → it generates a complete package.
-
-| Code | Description |
-|------|-------------|
-| **CA** | Create Agent — guided creation in 4 phases |
-| **QA** | Quick Agent — fast creation with sensible defaults |
-| **EA** | Edit Agent — modify an existing SKILL.md |
-| **VA** | Validate Agent — check BMAD+ compliance |
-| **PA** | Package Agent — generate the integration folder |
-
-**Pipeline:** Discovery → Design (user validation) → Generation → Validation
-**Output:** `_bmad-output/ready-to-integrate/` — ready to copy into BMAD+
-
----
-
-## 📦 Pack System
-
-BMAD+ uses a modular pack system. Core is always installed, additional packs are optional.
+Use when a version reaches your test environment and someone must check it on screen.
 
+```text
+Sentinel, write the acceptance recipe for this delivery on our test environment. One step per gesture, one verifiable fact per line, on-screen labels quoted from the code, and mark the steps that write for real. Build the page, then tell me the link, how long it takes and what I must not skip.
 ```
-npx bmad-plus install
-
-🎛️  Which packs to install?
-   Core (Atlas, Forge, Sentinel, Nexus) is always included.
-
-   🔍 OSINT — Shadow (investigation, scraping, psychoprofiling)
-   🧬 Agent Creator — Maker (design, build, package)
-   🛡️ Shield GRC — 27 compliance agents + 11 workflows (GDPR, ISO 27001, SOC 2, HIPAA...)
-   🏗️ Dev Studio — 6 SDLC agents (full lifecycle: design to deploy)
-   🔎 SEO Engine — Scout, Chief, Judge (6-phase audit, PageSpeed)
-   🧠 Memory — Zecher (persistent brain, session handoffs)
-   🗂️ Backup — Smart archive with versioning
-   🎬 Animated — Scroll-driven animated websites
-   🤖 Install everything
-   None — Core only
-```
-
-| Pack | Agents | Description | Status |
-|------|--------|-------------|--------|
-| ⚙️ **Core** | Atlas, Forge, Sentinel, Nexus | Strategy, dev, QA, orchestration | ✅ Stable |
-| 🔍 **OSINT** | Shadow | OSINT intelligence, 55+ Apify actors, 7 APIs | ✅ Stable |
-| 🧬 **Maker** | Maker | Design, build, validate new BMAD+ agents | ✅ Stable |
-| 🛡️ **Shield** | 27 GRC agents + 11 workflows | GDPR, ISO 27001, SOC 2, HIPAA, EU AI Act | ✅ Stable |
-| 🏗️ **Dev Studio** | 6 SDLC agents | Full lifecycle: design to deploy | ✅ Stable |
-| 🔎 **SEO** | Scout, Chief, Judge | 6-phase audit, PageSpeed loop, Google APIs | ✅ Stable |
-| 🧠 **Memory** | Zecher | Cross-session brain, decision recall, handoffs | ✅ Stable |
-| 🗂️ **Backup** | Backup Agent | Smart archive with versioning | ✅ Stable |
-| 🎬 **Animated** | Creative Agent | Scroll-driven animated websites | ✅ Stable |
-
-Each pack defines:
-- Its agents and skills
-- Its required/optional API keys
-- Its external package (if applicable)
-
----
-
-## ✨ Innovations
-
-### 1. 3-Level Intelligent Auto-Activation
-
-Each agent can **automatically** switch roles when the context requires it:
-
-| Level | Mechanism | Example |
-|--------|-----------|---------|
-| 🔤 **Pattern** | Keywords in the request | "review" → QA activated |
-| 🌐 **Contextual** | Domain detected during work | Financial calculations → QA auto-activated after code |
-| 🧠 **Reasoning** | Logic chain during execution | Architecture inconsistency → Architect auto-activated |
 
-The agent **announces** its auto-activations: *"💡 I'm switching to QA mode — financial calculations detected. Say 'skip' to stay in current mode."*
+Expected result: a page a non-technical person can play, and a run the agent reads back to classify every failure before anything is fixed.
 
-Configuration: `src/bmad-plus/data/role-triggers.yaml`
+### Resume without losing decisions
 
-### 2. Autopilot Mode
+Use at the start of a later session in the same project.
 
-Give a project idea → Nexus orchestrates the complete pipeline:
-
-```
-📋 Discovery (Atlas)
-  └→ Brainstorming → Product Brief → PRD → UX Design
-  🔴 CHECKPOINT: PRD Approval
-
-🏗️ Build (Forge + Sentinel)
-  └→ Architecture → Epics → Stories → Sprint
-  🔴 CHECKPOINT: Architecture Approval
-  └→ For each story: Code → Tests → (retry if failed, max 3)
-  🟡 NOTIFY: Story status
-
-🚀 Ship (Sentinel + Forge)
-  └→ Code Review → UX Review → Documentation → Retro
-  🔴 CHECKPOINT: Final approval
+```text
+Read AGENTS.md and the available project memory. Summarize the last verified state, open decisions and the next unfinished task. Check that the notes still match the code before continuing.
 ```
 
-**Configurable checkpoints:**
-Configure `execution_mode` and `checkpoints` in `_bmad/config.yaml` (`discovery`, `architecture`, `story`, `delivery`).
-
-- `require_approval` (🔴) — Pause, wait for approval
-- `notify_only` (🟡) — Notification, continues unless intervened
-- `auto` (🟢) — Continues automatically
-
-### 3. Supervised Parallel Execution
-
-The Orchestrator detects independent tasks and launches them in parallel:
-
-| Parallelizable ✅ | Sequential 🚫 |
-|---|---|
-| Stories without dependencies | Same file modified |
-| Research + tech audit | Story B depends on Story A |
-| Tests + documentation | Architecture before code |
-
-**Supervision actions:** Launch, Monitor, Stop, Restart, Reallocate, Escalate (3 failures → human notification)
-
----
-
-## 🖥️ Supported IDEs
-
-The installer automatically detects IDEs and generates their adapters around a shared `AGENTS.md` instruction spine at the project root:
+Expected result: a short, evidence-based restart. Project notes are useful context and still need to be checked against the current work.
 
-| IDE | Config File | Detection |
-|-----|---------------|-----------|
-| Claude Code | `CLAUDE.md` | `.claude/` folder |
-| Gemini CLI | `GEMINI.md` | `.gemini/` folder |
-| Antigravity | `GEMINI.md` | `.gemini/antigravity/` folder |
-| Cursor | `.cursor/rules/bmad-plus.mdc` | `.cursor/` folder |
-| Codex CLI | `.codex/AGENTS.md` | `.codex/` folder |
-| OpenCode | `.opencode/AGENTS.md` | `.opencode/` folder |
-| Aider | `CONVENTIONS.md` | `.aider.conf.yml` file |
+## What’s new in 0.16.0
 
-For Aider, add `read: CONVENTIONS.md` to `.aider.conf.yml` or run `/read CONVENTIONS.md` to load the generated instructions.
+Human acceptance, written down and read back
 
----
-
-## 📁 Project Structure
-
-```
-BMAD+/
-├── README.md                      ← This file (English)
-├── readme-international/          ← Translated READMEs (fr, es, de)
-├── CHANGELOG.md                   ← Version history
-├── CLAUDE.md                      ← Claude Code Config
-├── GEMINI.md                      ← Gemini CLI / Antigravity Config
-├── AGENTS.md                      ← Shared instruction spine
-├── .codex/AGENTS.md               ← Codex CLI adapter
-├── .opencode/AGENTS.md            ← OpenCode adapter
-├── .cursor/rules/bmad-plus.mdc    ← Cursor adapter
-├── CONVENTIONS.md                ← Aider adapter
-├── .gitignore
-│
-├── src/
-│   └── bmad-plus/                 ⭐ CUSTOM MODULE
-│       ├── module.yaml            ← Module + packs config
-│       ├── module-help.csv        ← Contextual help
-│       ├── agents/
-│       │   ├── agent-strategist/  ← Atlas (analyst + pm)
-│       │   ├── agent-architect-dev/ ← Forge (architect + dev + tw)
-│       │   ├── agent-quality/     ← Sentinel (qa + ux)
-│       │   ├── agent-orchestrator/ ← Nexus (sm + qf + autopilot + parallel)
-│       │   ├── agent-maker/       ← Maker (meta-agent) [pack: maker]
-│       │   └── agent-shadow/      ← Shadow (osint) [pack: osint]
-│       ├── skills/
-│       │   ├── bmad-plus-autopilot/ ← Automated pipeline
-│       │   └── bmad-plus-parallel/  ← Parallel execution
-│       └── data/
-│           └── role-triggers.yaml ← Auto-activation rules
-│
-├── tools/
-│   └── cli/                       🛠️ NPX INSTALLER
-│       └── install.js             ← npx bmad-plus install
-│
-├── osint-agent-package/           🔍 OSINT PACKAGE
-│   ├── agents/                    ← Shadow Agent (OSINT investigator)
-│   ├── skills/                    ← 55+ Apify actors
-│   └── install.ps1                ← Installation script
-│
-└── upstream/                      📦 UPSTREAM REFERENCE
-    └── (clone of BMAD-METHOD)     ← Excluded from repo (.gitignore)
-```
+A delivery now produces a step-by-step page a person plays, and their run comes back as evidence the agents read, classify and gate on. This release also carries what 0.15.0 had prepared and never shipped: durable Nexus execution, evidence-ranked memory and scored checks for every pack.
 
----
+- bmad-plus uat builds a self-contained acceptance page from a JSON specification: one verifiable fact per line, on-screen labels quoted from your own code, and every step that writes for real marked as such.
+- The tester answers Seen, Not seen or Blocked and writes what they saw instead. Answers are saved as they go — straight into the project with uat serve, or in the page itself when it travels as a file.
+- uat read returns every failure with its expectation and the tester note; uat gate passes only when the run is finished, answers the current revision of the recipe, is fully classified, and every writing step was confirmed read-only.
+- The page speaks the ten languages of the installer, opens in the project language and lets the tester switch. Sentinel gains a Recette role, and the delivery report quotes the run instead of claiming acceptance.
+- Nexus records task dependencies, write scopes, attempts and recovery evidence. Use nexus create --plan plan.json, then nexus launch RUN TASK for an explicitly configured command or Codex CLI process.
+- After launch, inspect the run, collect its exact attempt identity, run nexus verify RUN TASK and finally nexus accept RUN TASK. A finished process or an agent's success message cannot replace independent checks; host permissions still apply.
+- mem observe --input observation.json links one project memory section to a currently accepted Nexus task. mem recall QUERY --ranking evidence --context-scope PATH rechecks the evidence; stale, superseded or explicitly conflicting advice is excluded.
+- All nine packs have scored deterministic replay checks with negative controls. A small native pilot and repeated-campaign tooling keep real model observations separate from replay results; no general model-quality gain is claimed.
+- The release workflow checks a production dependency SBOM, publishes the exact validated archive and compares npm integrity before updating this site. Source notices ship with the package; npm provenance is not enabled.
+- Existing project update policies and customized-file protections remain in force. Restart the assistant or reload AGENTS.md and the affected skills after applying the update.
 
-## ⚙️ Configuration
+## Version History
 
-### Module variables (`module.yaml`)
+These dates identify reviewed CHANGELOG notes, not npm publication dates. The website verifies npm publication dates separately.
 
-| Variable | Description | Values |
-|----------|-------------|---------|
-| `project_name` | Project name | Auto-detected |
-| `user_skill_level` | Dev level | beginner, intermediate, expert |
-| `execution_mode` | Execution mode | manual, autopilot, hybrid |
-| `auto_role_activation` | Role auto-switch| true, false |
-| `parallel_execution` | Parallelism | true, false |
-| `install_packs` | Installed packs | core, osint, maker, audit, all |
+| Version | Release-notes date | Reviewed summary |
+| --- | --- | --- |
+| 0.16.0 | 2026-09-16 | A delivery now produces a step-by-step page a person plays, and their run comes back as evidence the agents read, classify and gate on. This release also carries what 0.15.0 had prepared and never shipped: durable Nexus execution, evidence-ranked memory and scored checks for every pack. |
+| 0.14.0 | 2026-09-09 | Dev Studio gains complete instructions and verifiable context loading; release documentation follows the published package. |
+| 0.13.0 | 2026-09-08 | Discover published releases, control automatic-update policy and preserve customized agent files. |
 
-### API Keys (depending on packs)
-
-| Key | Pack | Usage |
-|-----|------|-------|
-| `APIFY_API_TOKEN` | OSINT | Social media scraping |
-| `PERPLEXITY_API_KEY` | OSINT | Enriched search |
-
----
-
-## 📜 Version History
-
-| Version | Date | Description |
-|---------|------|-------------|
-| **0.1.0** | 2026-03-17 | 🎉 Foundation — 6 agents (Atlas, Forge, Sentinel, Nexus, Shadow, Maker), 3 skills, pack system, multi-IDE support |
-| **0.2.0** | 2026-03-18 | 🔀 Oveanet Fusion — 3 new utility packs: SEO Audit 360, Universal Backup, Animated Website |
-| **0.3.0** | 2026-03-19 | 🚀 SEO Engine v2.0 — 3 multi-role agents, 4 Python scripts, 6-phase workflow, PageSpeed loop, GEO analysis |
-| **0.4.0** | 2026-03-19 | 🏢 SEO Engine v2.1 — SKILL.md orchestrator, Google APIs, HTML reports, competitor benchmark, 50 tests, GSC + GA4 extensions |
-| **0.4.1** | 2026-03-19 | 🌐 10-language CLI, CI/CD pipeline, `.npmignore`, security hardening |
-| **0.4.2** | 2026-03-19 | 📦 Public packs — SEO/Backup/Animated agents now in npm package |
-| **0.4.3** | 2026-05-17 | 🔧 update + doctor commands, i18n complete, credits fix |
-| **0.4.4** | 2026-05-17 | 🔧 UTF-8 encoding fix, complete i18n 10 languages, 62 unit tests |
-| **0.5.0** | 2026-05-17 | 🛡️ **Pack Shield** — 27 GRC compliance agents + 11 workflows, 6 categories, 25+ frameworks (GDPR, ISO 27001, SOC 2, EU AI Act...) |
-| **0.6.0** | 2026-05-17 | 🏗️ **Pack Dev Studio** — 6 SDLC agents (Miriam, Yosef, Bezalel...) + 30 SDLC workflows, BWML DSL |
-| **0.8.0** | 2026-06-24 | 🚀 **Augmented** — 3 new packs (animated, backup, seo), security remediation pass, i18n sync |
-| **0.9.0** | 2026-06-24 | 🔒 **Secure** — audit remediation cycle, npm audit clean, shared pack registry (`lib/packs.js`) |
-
-See [CHANGELOG.md](CHANGELOG.md) for full details.
+[Release history and update guide](https://bmad-plus.rochetta.fr/docs/#changelog) · [All published npm versions](https://www.npmjs.com/package/bmad-plus?activeTab=versions)
 
 ---
 
@@ -563,6 +186,9 @@ See [CHANGELOG.md](CHANGELOG.md) for full details.
 
 MIT — Based on [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (MIT)
 
+BMAD+ is an independent derivative, not an official BMad Code, LLC release or endorsement.
+Bundled source attributions and terms: [Third-party notices](THIRD-PARTY-LICENSES.md).
+
 ### Credits
 
 **Creator**
@@ -575,10 +201,10 @@ MIT — Based on [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (MI
 
 **External Sources & Inspirations**
 - **BMAD-METHOD** by [bmad-code-org](https://github.com/bmad-code-org/BMAD-METHOD) — Original multi-agent methodology (MIT)
-- **Shield GRC** — 27 compliance agents + 11 workflows built on public regulatory texts (GDPR, ISO 27001, SOC 2, HIPAA, EU AI Act, DORA, NIST, CMMC, etc.)
+- **Shield GRC** — 27 compliance agents + 11 workflows adapted from [Hemant Naik's GRC skills](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance) (MIT)
 - **OSINT Pipeline** based on [smixs/osint-skill](https://github.com/smixs/osint-skill) (MIT)
-- **Apify Actor Runner** integrated from [apify/agent-skills](https://github.com/apify/agent-skills) (MIT)
-- **Karpathy Guardrails** adapted from [Andrej Karpathy](https://github.com/multica-ai/andrej-karpathy-skills) (MIT) — Behavioral rules for Memory Pack
+- **Apify integration** — OSINT helper and inspiration from [Apify agent skills](https://github.com/apify/agent-skills) (upstream declares Apache-2.0; see notices)
+- **Karpathy Guardrails** — Memory Pack adaptation of [community guidelines by forrestchang](https://github.com/multica-ai/andrej-karpathy-skills), inspired by Andrej Karpathy (MIT declared upstream)
 
 **Tools & Infrastructure**
 - [Evolution API](https://github.com/EvolutionAPI/evolution-api) — WhatsApp notifications for upstream monitoring